{"data":{"id":"meta-llama-3-3-70b-instruct-turbo","name":"llama-3-3-70b-instruct-turbo","display_name":"Llama 3.3 70B Instruct Turbo","description":"FP8-quantized turbo variant of Llama 3.3 70B Instruct, delivering significantly faster inference speeds with minimal accuracy trade-off.","creator":"meta","family":"llama","tier":"","version":"3-3","type":"language","size_in_bn":70,"modalities":{"input":["text"],"output":["text"]},"context_window":131072,"max_output_tokens":null,"tool_use_system_prompt_tokens":0,"output_vector_sizes":[],"knowledge_cutoff":null,"training_data_cutoff":null,"supported_reasoning_efforts":[],"tokenizer":null,"capabilities":{"function_calling":true,"parallel_function_calling":true,"structured_outputs":true,"prompt_caching":false,"reasoning":false,"web_search":false,"computer_use":false,"code_execution":false,"file_search":false,"url_context":false,"assistant_prefill":false,"native_structured_output":false,"adaptive_reasoning":false},"release_date":null,"earliest_deprecation_date":null,"deprecated":false,"has_pricing":true,"provider_count":3,"ids":["deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo","meta-llama-3-3-70b-instruct-turbo","meta-llama/Llama-3.3-70B-Instruct-Turbo","together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo"],"hf_likes":null,"hf_downloads":null,"hf_downloads_all_time":null,"hf_trending_score":null,"updated_at":"2026-06-19 08:02:10"},"meta":{"updated_at":"2026-06-19","request_id":"608c6207-2e43-4ade-97d9-c368b63525c1","execution_ms":10}}